Multi- forword-step state of charge prediction for real-world electric vehicles battery systems using a novel LSTM-GRU hybrid neural network

Battery state-of-charge (SOC) is an evaluation metric for the electric vehicles' remaining driving range and one of the main monitoring parameters for battery management systems. However, there are rarely data-driven studies on multi-step prediction of battery SOC, which cannot accurately provide and realize electric vehicle remaining driving range prediction and SOC safety pre-warning. Therefore, this study aims to perform SOC multi-forward-step prediction for real-world vehicle battery system by a novel hybrid long short-term memory and gate recurrent unit (LSTM-GRU) neural network. The paper firstly analyses the characteristics of correlation analysis and adopts similarity metric method to reduce the parameter dimensionality for the input neural network. Then the advantages between LSTM-GRU, LSTM, GRU, and long short-term memory and convolutional neural network (LSTM-CNN) are analyzed by comparing experimental and real-world vehicle data, and the effectiveness and accuracy of the proposed method is demonstrated. In addition, the proposed method robustness is verified by adding noise data to the input parameters. In this study, the prediction results were validated with real-world vehicle data in spring, summer, autumn and winter, and the proposed method achieved a minimum MAPE and MAE of 1.03% and 0.73 for summer conditions, while the minimum standard deviation of prediction was 0.06% for experimental conditions. The research process shows that the method has high accuracy when applied to large data and is expected to be applied to real-world vehicle battery system SOC multi-forward-step prediction in the future.

• Record URL:
  • https://doi.org/10.1016/j.etran.2024.100322
• Record URL:
  • http://www.sciencedirect.com/science/article/pii/S2590116824000122
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/25901168
• Supplemental Notes:
  • © 2024 Elsevier B.V. All rights reserved. Abstract reprinted with permission of Elsevier.
• Authors:
  • Hong, Jichao
  • 0000-0001-5265-3466
  • Liang, Fengwei
  • Yang, Haixu
  • Zhang, Chi
  • Zhang, Xinyang
  • Zhang, Huaqin
  • Wang, Wei
  • Li, Kerui
  • Yang, Jingsong
• Publication Date: 2024-5

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: 100322
• Serial:
  • eTransportation
  • Volume: 20
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 2590-1168
  • Serial URL: https://www.sciencedirect.com/journal/etransportation

Subject/Index Terms

• TRT Terms: Electric batteries; Electric vehicle charging; Electric vehicles; Neural networks; Predictive models
• Subject Areas: Energy; Highways; Vehicles and Equipment;

Filing Info

• Accession Number: 01912643
• Record Type: Publication
• Files: TRIS
• Created Date: Mar 20 2024 5:08PM